Adrien Bousseau is a Senior Researcher at Inria within the GraphDeco group at Université Côte d'Azur. He earned his PhD from Inria Rhône-Alpes under Joëlle Thollot and François X. Sillion, with internships at Adobe and MIT. His postdoctoral research at UC Berkeley focused on computational design and graphics. Notable roles include leading the ANR DRAO project (2012–2015) and coordinating the CRISP associate team with UC Berkeley. He has received prestigious awards such as the Eurographics 2011 PhD Award and ERC grants for projects on 3D design and circular design. Research interests span image creation, stylization, vector graphics, and sketch-based modeling. Recent work explores computational methods for circular design and AI-driven design tools. He has supervised over 13 PhD students, including Nicolas Rosset (aerodynamics) and Emilie Yu (VR sketching). Key projects include ERC-funded initiatives on drawing interpretation and material acquisition. Service contributions include co-chairing Eurographics 2025 and EGSR 2021, and editorial roles at Computer Graphics Forum. Publicly accessible tools include Photoshop watercolor filters and academic resources like BendFields tutorials.
Weihao Xia is a postdoctoral researcher at the University of Cambridge's Department of Computer Science and Technology, affiliated with the CORE Lab under Cengiz Öztireli. His work bridges computer science and human cognition, focusing on multimodal learning, brain decoding, and tactile representation. He specializes in integrating visual, textual, neural, and tactile data to enhance AI systems for perception and creativity. Research interests include neural decoding from brain signals, tactile representation learning, and generative models for cross-modal translation. Notable projects include UMBRAE (unified multimodal brain decoding) and DREAM (visual decoding via human visual system reversal). His work addresses challenges in generating realistic images, interpreting neural signals, and improving tactile-based material editing. Teaching: Supervises Part II, Part III, and M.Phil. projects at Cambridge. Research topics for students include brain-based art creation, tactile material editing, and benchmarking sensory modalities. Projects emphasize multimodal alignment, brain-imagery reconstruction, and tactile representation learning. Contact: wx258@cam.ac.uk | Room GC01, William Gates Building.
Leonidas Guibas is the Paul Pigott Professor of Engineering and Professor (by courtesy) of Electrical Engineering at Stanford University's Department of Computer Science. He leads the Geometric Computation group and is affiliated with the Computer Graphics and Artificial Intelligence Laboratories. His research focuses on algorithms for sensing, modeling, and reasoning about the physical world, with expertise in computational geometry, robotics, sensor networks, and topological data analysis. Current work includes geometric modeling with point clouds, 3D reconstruction, and mobility data analysis. He holds prestigious awards including ACM Fellow (1999), Allen Newell Award (2008), and membership in the National Academy of Sciences (2022). Education: PhD, Stanford University (1976) MS & BS, California Institute of Technology (1971) Research Interests: Geometric and topological data analysis 3D reconstruction and 3D shape analysis Sensor networks and robotics Biological structure modeling Machine learning for geometric problems Recent Articles Focus: Recent work emphasizes neural radiance fields (NeRF), dynamic Gaussian splatting, and physically plausible 3D shape generation. Publications span advancements in symmetry detection, articulated object manipulation, and multi-view video generation. Awards & Honors: Fellow, ACM (1999) Allen Newell Award (2008) Fellow, IEEE (2011) Member, National Academy of Engineering (2017) Member, National Academy of Sciences (2022) Advising & Teams: Advises doctoral and master's students on topics like geometric computing and robotics. Leads interdisciplinary teams at Stanford's ICME, HAI, and Woods Institute. Current advisees include Ian Huang, Boxiao Pan, and Colton Stearns. Labs & Collaborations: Active in the Geometric Computation group and collaborates with the Stanford AI Lab. Works on projects funded by grants in robotics, computer vision, and computational biology.
Alexei Efros is a Professor of Electrical Engineering and Computer Science at UC Berkeley , affiliated with the Berkeley Artificial Intelligence Research Lab (BAIR) . Previously, he was a faculty member at the Robotics Institute, Carnegie Mellon University , and a postdoc at Oxford University with Andrew Zisserman. His work spans data-driven computer vision , self-supervised learning , and applications to computer graphics , computational photography , and human-AI interaction . Research Themes : Self-supervised visual learning 3D scene understanding Vision-language multimodal systems Teaching : CS 180/280A: Intro to Computer Vision CS 280: Graduate Computer Vision CS 294-192: Visual Scene Understanding Recent Publication Trends : Focus on diffusion models and self-guidance 3D perception and rendering Interpretability of vision-language models Temporal and sequential learning Scientific Collaborations : Extensive partnerships with institutions like MIT, CMU, Stanford, and NVIDIA Mentorship of PhD students now at TTIC, OpenAI, Anthropic, and academia Labs & Teams : BAIR Lab (UC Berkeley) Collaborations with Adobe Research, Google, and NVIDIA
Yue Jiang is an incoming Assistant Professor at the University of Utah (Fall 2025) and is completing their PhD at Aalto University and the Finnish Center for Artificial Intelligence (FCAI). Their research focuses on computational user interface understanding, eye tracking, and adaptive GUI layouts. They have held roles such as Accessibility Chair for CHI2023/2024 and have organized workshops on computational UI methodologies. Education : PhD in Intelligent Systems (Aalto University & FCAI, Finland) Visiting PhD Student (CMU's BIG Lab, 2024) Master's in Computer Graphics (UMD, USA) Bachelor's in Computer Science & Mathematics (U of Toronto, Canada) Research Interests : Developing human-centered technologies for adaptive UIs, eye tracking analysis, and AI-driven HCI. Key projects include Graph4GUI, EyeFormer, and computational methods for GUI layout optimization. Awards : Meta PhD Fellowship (2023-2025) Google Europe Students with Disabilities Scholarship (2022) CHI2022 Best Paper Honorable Mention Heidelberg Laureate Forum Young Researcher (2024) Service : PC Member for VL/HCC2025, CHI2026 Associate Chair for CHI2025/2026 Organized three Computational UI Workshops at CHI Labs & Collaborations : Collaborates with Prof. Jeffrey Bigham (CMU), Prof. Wolfgang Stuerzlinger (SFU), and Prof. Christof Lutteroth (U of Bath). Former internships at Apple AIML Lab and Adobe Research.
Mark Burkhardt is a doctoral researcher and research associate at the Institute for System Dynamics within the Cluster of Excellence IntCDC at the University of Stuttgart. His work focuses on control systems and automation technologies for construction machinery, particularly tower cranes. Current affiliation: Institute for System Dynamics, University of Stuttgart Academic rank: Researcher Specializations: Crane control systems, cyber-physical construction platforms, automation of timber structures Research Interests: Burkhardt's research spans control systems engineering, automation technologies, and cyber-physical systems. His work addresses critical challenges in: Load sway damping for top-slewing cranes Path planning and absolute positioning of tower cranes Modeling and control of collaborative crane systems Development of novel grab systems for construction automation Georeferenced payload tracking Multi-agent crane coordination Teaching: He has taught courses on system dynamics, control theory, and programming since 2019, including: "Flache Systeme" (Flat Systems) "Systemdynamische Grundlagen der Regelungstechnik" (System Dynamics Fundamentals of Control Engineering) "Einführung in die Programmiersprache C" (Introduction to C Programming) "Praktikum Automatisierungstechnik/Systemdynamik" (Automation/System Dynamics Practical) Education: He holds an M.Sc. in Technical Cybernetics from the University of Stuttgart (2016-2019) and a B.Sc. in the same field (2013-2016).
Jesús Tordesillas Torres is an Assistant Professor in the Department of Electronics, Automation, and Communications at the School of Engineering, Comillas Pontifical University. He joined the institution in June 2024, bringing extensive experience from postdoctoral research at MIT and ETH Zurich, and prior academic training from MIT and the Polytechnic University of Madrid. Education: PhD in Aeronautics and Astronautics, Massachusetts Institute of Technology (MIT), 2022 MS in Aeronautics and Astronautics, MIT, 2019 MS in Industrial Engineering, Polytechnic University of Madrid, 2019 BS in Industrial Engineering, Polytechnic University of Madrid, 2016 His research focuses on robotics, particularly autonomous navigation, trajectory planning, and optimization under uncertainty. He integrates deep learning and control theory to develop systems capable of safe, fast, and perception-aware navigation in dynamic and unknown environments. His work spans aerial and ground robots, multiagent systems, and challenging terrains, with strong emphasis on real-world deployment and robustness. The recent publications highlight a consistent trend in trajectory optimization, perception-aware planning, and multiagent coordination. His work bridges theoretical advances in optimization and learning with practical robotic applications, especially in safety-critical and communication-constrained scenarios. Scientific Awards: Best Paper Award, IEEE ICRA 2023 1st Place, Urban Circuit, DARPA Subterranean Challenge (2020) 2nd Place, Tunnel Circuit, DARPA Subterranean Challenge (2021) Finalist, Best Paper, IEEE IROS 2019 Jesús Tordesillas Torres has been actively involved in research grants and projects, including the ADS FERRARI WP-2 Project funded by Airbus Defence and Space (2025–2025). He mentors students and collaborates with leading institutions such as MIT, ETH Zurich, and the University of Pennsylvania. He also serves as a reviewer for top-tier journals including IEEE Transactions on Robotics , International Journal of Robotics Research , and IEEE Robotics and Automation Letters , as well as major conferences like ICRA and IROS. He leads and participates in research teams focused on autonomous systems, with affiliations to the Institute for Research in Technology (IIT) at Comillas. His invited talks at ETH Robotics Summer School and University of Pennsylvania reflect his growing influence in the robotics community.
Prof. Dr. Frank Haußer is a Professor at Beuth University of Applied Sciences Berlin in the Department II Mathematics - Physics - Chemistry. He serves as the academic advisor for the Applied Mathematics program and teaches courses including Numerical Mathematics, Mathematical Methods of Digital Image Processing, and Computational Engineering. His consultation hours are held during semesters and by appointment, with availability both in-person and online. Haußer's research focuses on: Numerical mathematics and scientific computing Mathematical modeling with applications in MATLAB/Octave Machine learning for medical imaging and insect monitoring Digital image processing techniques for biomedical applications Partial differential equations and computational engineering methods He has authored a textbook on mathematical modeling with MATLAB/Octave and leads interdisciplinary projects at the intersection of mathematics and technology. Analysis of his 15 most recent publications shows strong emphasis on: Medical imaging algorithms (especially retinal OCT analysis) Nanostructure dynamics and material science Computational physics and finite element methods Machine learning applications in biology and medicine Advanced mathematical modeling techniques His work consistently bridges theoretical mathematics with practical engineering applications. Haußer actively supervises student research, including: Machine learning for insect classification and localization Medical image processing algorithms Computational methods in engineering Finite element analysis applications Optimization and simulation techniques He has guided over 30 bachelor's and master's theses since 2009. His research projects include: KInsekt (2020-2023): AI-based insect monitoring funded by BMUV BeCRF (2015-2017): Medical image quality validation funded by BMWi QM ROCT (2013-2015): Automated OCT quality management funded by IFAF These interdisciplinary collaborations involve institutions across Germany.
Zihan Zhou is an Assistant Professor at the College of Information Sciences and Technology, Penn State University, specializing in computer vision, machine learning, and 3D reconstruction. His research bridges geometric modeling, image processing, and human-computer interaction, with applications in assistive technology and creative design. Email: zuz22@psu.edu His work focuses on robust face recognition, sparse representation, and vision-language approaches for converting 2D CAD drawings into 3D parametric models. Recent projects include neural rendering for wireframe-to-image translation and data-driven 3D scene modeling. The 15 most recent publications highlight his contributions to end-to-end floorplan generation, depth estimation, trajectory prediction, and structured 3D modeling. These works integrate convolutional neural networks, graph construction, and optimization algorithms. Projects like Building Energy Savings by Tuning Indoor Lighting underscore his interdisciplinary approach, combining computer vision with environmental sustainability.
Joan Lasenby is a Professor of Image and Signal Analysis at the Department of Engineering , University of Cambridge. She is affiliated with the Cambridge Mathematics of Information in Healthcare Hub (CMIH) . Research focuses on advanced motion capture, geometric algebra applications, and healthcare technology Key contributions to 3D reconstruction, camera pose estimation, and biomedical sensor fusion Recent work spans neonatal monitoring, protein structure modeling, and fluid dynamics simulations Her publications demonstrate strong expertise in combining geometric algebra with deep learning for diverse applications in computer vision, biomedicine, and physics simulations. As part of the Cambridge Engineering faculty, she contributes to interdisciplinary research at the intersection of mathematics, computer science, and healthcare technology.
Ignacio IZEDDIN is an Associate Professor ( Maître de conférences ) at the Institut Langevin, ESPCI Paris, which is part of CNRS and Université PSL. His research sits at the critical intersection of advanced optical imaging, biophysics, and molecular cell biology, with a particular focus on pushing the boundaries of what can be visualized and understood about molecular distribution and cellular dynamics. His primary research interests include Single-Molecule Localization Microscopy (SMLM), super-resolution imaging techniques, single particle tracking (SPT), biophotonics, diffusion processes in cell biology, molecular cell biology, transcription regulation, DNA repair mechanisms, and light-matter interactions at the nanoscale. Dr. IZEDDIN's work aims to develop innovative microscopy tools that overcome current limitations in spatial and temporal resolution, enabling the capture of rapid, dynamic cellular processes with unprecedented clarity. The trends in his recent publications reveal a strong focus on developing event-based sensor technology for high-speed single-molecule localization, creating novel 3D microstructured substrates for cellular imaging and calibration, studying light-matter interactions at the nanoscale through fluorescence lifetime imaging, and applying these advanced techniques to understand fundamental biological processes like DNA repair, chromatin dynamics, and cellular differentiation. His work consistently bridges physics, engineering, and biology to solve complex imaging challenges. Dr. IZEDDIN is actively involved in research funding and recruitment, with current projects including a European LIGHTinParis COFUND PhD position analyzing alpha-synuclein diffusion in neurons using super-resolution microscopy based on event sensors, and hiring for a software engineer position to develop data processing tools for event-based SMLM technology. His laboratory employs a highly interdisciplinary approach, combining physics, biology, and engineering expertise to tackle challenging problems in cellular imaging. Current projects involve collaborations with neuroscientists, physicists, and engineers to study everything from molecular diffusion in neurons to macrophage differentiation on 3D topographical substrates.
Dr Simon Lock is a Senior Lecturer at the School of Computer Science, University of Bristol. His research and public engagement focus on pragmatic software engineering, open data, citizen science, and interactive applications for social spaces, with an emphasis on data visualization and IoT platforms. He can be contacted at simon.lock@bristol.ac.uk . Education : Not explicitly mentioned in the text. Simon's research interests span software engineering applications in educational and social contexts, including engineering education best practices, teaching and learning innovations, and the use of technology for public engagement. His publications (via ORCID) include seminal works on planetary collisions, lunar formation, and tidal evolution, indicating interdisciplinary contributions bridging computational methods and planetary science. His recent work explores planetary impacts and their thermodynamic consequences, atmospheric loss in giant collisions, and high-level models for Earth-Moon tidal evolution. Despite his computer science role, his research outputs extend deeply into astrophysics and geophysics, particularly Moon-forming giant impacts and planetary differentiation. Grants : Not explicitly mentioned in the text. Labs/Teams : Affiliated with the Engineering Education Research Group and the UK & IE EER Network.
Nitin J Sanket is an Assistant Professor in the Robotics Engineering Department at Worcester Polytechnic Institute, where he leads the Perception and Autonomous Robotics Group (PeAR) founded in 2022. His research focuses on advancing autonomy for tiny mobile robots through bio-inspired approaches that enable on-board sensing and computation without external infrastructure. Ph.D. in Computer Science from University of Maryland, College Park (2021) M.S. in Robotics from University of Pennsylvania (2016) B.E. in Electronics and Communication from M. S. Ramaiah Institute of Technology, Bangalore, India (2013) Professor Sanket's research centers on four interconnected thrusts: Active perception (using movement to simplify perception problems), Interactive perception (selectively interacting with the environment), Novel perception (using data statistics like neural network uncertainty), and Novel sensing (employing sensors like event cameras). His work targets extreme resource-constrained robots, exemplified by the world's first RoboBeeHive prototype – hummingbird-sized nano-quadrotors capable of pollination with all sensing and computation performed on-board. His lab's 'Minimal-AI' philosophy emphasizes efficiency, using perception-action synergy to solve complex problems with minimal computational resources. His recent publications reveal a strong focus on efficient vision algorithms for tiny robots, with papers in Science Robotics (featured on the cover), IEEE ICRA, IROS, and CVPR. Key themes include uncertainty modeling for resource-constrained systems, event-based vision, and bio-inspired navigation. His work frequently bridges theoretical innovation with practical implementation on real hardware. Larry S. Davis Award for Best Computer Science PhD Thesis at University of Maryland (2021) MDPI Drones 2021 PhD Thesis Award Brin Family Prize (2018) Science Robotics cover feature (2023) Professor Sanket actively mentors 19 students (3 PhD, 6 Masters, 10 undergraduates) and recently secured a $705K NSF grant (September 2025) for bio-inspired sound navigation in tiny robots. His lab emphasizes hands-on experience with real hardware systems rather than pure simulation. His research on bat-inspired drones for search and rescue operations has received extensive media coverage from Associated Press, Washington Post, NPR, and other major outlets, demonstrating the real-world relevance of his work. The Perception and Autonomous Robotics Group (PeAR) provides students with opportunities to work on cutting-edge problems in nano-drone development, bio-inspired navigation, and minimal-AI approaches, preparing them for careers at the forefront of robotics innovation.
David Coeurjolly is a Research Director at the French National Center for Scientific Research (CNRS) affiliated with LIRIS laboratory at Claude Bernard University Lyon 1. He leads the Origami research team and holds several leadership positions including Director of GdR Informatique Géométrique et Graphique and Co-lead of PEPR ICCARE. As co-founder of the DGtal library and General Chair of the Graphics Replicability Stamp Initiative, he significantly influences computational geometry research. His research spans digital geometry, discrete algorithms, Monte Carlo rendering, and geometry processing. Core innovations include work on optimal transport, low-discrepancy sampling, digital surface regularization, and curvature estimation methods. His approaches combine theoretical mathematics with practical implementations for computer graphics and scientific computing applications. Recent publications demonstrate strong focus on: Efficient transport algorithms (BSP-OT, Rectified Flows) Sampling theory innovations (Sobol' sequences, Owen scrambling) Digital geometry foundations (Gauss digitization, Laplace-Beltrami operators) Geometric transformations (bijective rotations, plane probing) Awards include: 🎫 Best Paper Award, SIGGRAPH Asia 2024 🎫 SGP Software Award 2016 He leads multiple ANR grants including SSLAM (point cloud ML), StableProxies (geometry processing), and MoCaMed (medical physics). His lab develops open-source tools like DGtal and maintains active collaborations through international initiatives like the Graphics Replicability Stamp.
Gilbert Bernstein is an Assistant Professor in the Computer Science & Engineering department within the College of Engineering at the University of Washington. His research bridges computer graphics and programming languages, with a focus on high-performance domain-specific languages. Previously, he was a post-doctoral scholar at UC Berkeley and MIT working with Jonathan Ragan-Kelley, and received his PhD from Stanford University under Pat Hanrahan. His research interests span Computer Graphics, Programming Languages, High-Performance DSLs, Physical Simulation, Geometry & Topology, Differentiable Programming, Hardware DSLs, Tools for Artists, Fabrication, and Human-Computer Interaction. Bernstein develops languages and compilers that enable efficient computation for creative applications, physical simulations, and graphics rendering systems. His recent publications reveal strong trends in differentiable programming for graphics applications, domain-specific languages for hardware acceleration, and computational approaches to traditional crafts like quilting and knitting. His work consistently combines formal language theory with practical applications in graphics and fabrication. Bernstein actively mentors students across multiple institutions including current advisees Felix Hahnlein (UW Postdoc), Ryan Zambrotta (UW PhD), Haoran Peng (UW PhD), and previous students including Alex Reinking (UC Berkeley PhD 2022, now at Qualcomm) and MacKenzie Leake (Stanford PhD 2021, now at Adobe Research). His lab works on diverse projects including debugging CAD programs, compilers for finite element methods, semantics for knitting machines, algebraic scheduling of tensor programs, and exocompilers for hardware accelerators. Bernstein also collaborates on DSLs for networking, Counterstrike bots, gradient-based optimization, memory management, hardware design, and garment design tools.
